Look Through Masks: Towards Masked Face Recognition with De-Occlusion Distillation

• URL: http://arxiv.org/abs/2409.12385v1
• Date: Thu, 19 Sep 2024 01:00:36 GMT
• Title: Look Through Masks: Towards Masked Face Recognition with De-Occlusion Distillation
• Authors: Chenyu Li, Shiming Ge, Daichi Zhang, Jia Li,
• Abstract summary: We propose to migrate the mechanism of amodal completion for the task of masked face recognition with an end-to-end de-occlusion distillation framework. The textitde-occlusion module applies a generative adversarial network to perform face completion, which recovers the content under the mask and eliminates appearance ambiguity. The textitdistillation module takes a pre-trained general face recognition model as the teacher and transfers its knowledge to train a student for completed faces.
• Score: 39.159835055226274
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Many real-world applications today like video surveillance and urban governance need to address the recognition of masked faces, where content replacement by diverse masks often brings in incomplete appearance and ambiguous representation, leading to a sharp drop in accuracy. Inspired by recent progress on amodal perception, we propose to migrate the mechanism of amodal completion for the task of masked face recognition with an end-to-end de-occlusion distillation framework, which consists of two modules. The \textit{de-occlusion} module applies a generative adversarial network to perform face completion, which recovers the content under the mask and eliminates appearance ambiguity. The \textit{distillation} module takes a pre-trained general face recognition model as the teacher and transfers its knowledge to train a student for completed faces using massive online synthesized face pairs. Especially, the teacher knowledge is represented with structural relations among instances in multiple orders, which serves as a posterior regularization to enable the adaptation. In this way, the knowledge can be fully distilled and transferred to identify masked faces. Experiments on synthetic and realistic datasets show the efficacy of the proposed approach.

Related papers

• Masked Face Recognition with Generative-to-Discriminative Representations [29.035270415311427]
  We propose a unified deep network to learn generative-to-discriminative representations for facilitating masked face recognition. First, we leverage a generative encoder pretrained for face inpainting and finetune it to represent masked faces into category-aware descriptors. We incorporate a multi-layer convolutional network as a discriminative reformer and learn it to convert the category-aware descriptors into identity-aware vectors.
  arXiv  Detail & Related papers  (2024-05-27T02:20:55Z)
• Seeing through the Mask: Multi-task Generative Mask Decoupling Face Recognition [47.248075664420874]
  Current general face recognition system suffers from serious performance degradation when encountering occluded scenes. This paper proposes a Multi-task gEnerative mask dEcoupling face Recognition (MEER) network to jointly handle these two tasks. We first present a novel mask decoupling module to disentangle mask and identity information, which makes the network obtain purer identity features from visible facial components.
  arXiv  Detail & Related papers  (2023-11-20T03:23:03Z)
• MM-3DScene: 3D Scene Understanding by Customizing Masked Modeling with Informative-Preserved Reconstruction and Self-Distilled Consistency [120.9499803967496]
  We propose a novel informative-preserved reconstruction, which explores local statistics to discover and preserve the representative structured points. Our method can concentrate on modeling regional geometry and enjoy less ambiguity for masked reconstruction. By combining informative-preserved reconstruction on masked areas and consistency self-distillation from unmasked areas, a unified framework called MM-3DScene is yielded.
  arXiv  Detail & Related papers  (2022-12-20T01:53:40Z)
• A Unified Framework for Masked and Mask-Free Face Recognition via Feature Rectification [19.417191498842044]
  We propose a unified framework, named Face Feature Rectification Network (FFR-Net), for recognizing both masked and mask-free faces alike. We introduce rectification blocks to rectify features extracted by a state-of-the-art recognition model, in both spatial and channel dimensions. Experiments show that our framework can learn a rectified feature space for recognizing both masked and mask-free faces effectively.
  arXiv  Detail & Related papers  (2022-02-15T12:37:59Z)
• Segmentation-Reconstruction-Guided Facial Image De-occlusion [48.952656891182826]
  Occlusions are very common in face images in the wild, leading to the degraded performance of face-related tasks. This paper proposes a novel face de-occlusion model based on face segmentation and 3D face reconstruction.
  arXiv  Detail & Related papers  (2021-12-15T10:40:08Z)
• Mask-invariant Face Recognition through Template-level Knowledge Distillation [3.727773051465455]
  Masks affect the performance of previous face recognition systems. We propose a mask-invariant face recognition solution (MaskInv) In addition to the distilled knowledge, the student network benefits from additional guidance by margin-based identity classification loss.
  arXiv  Detail & Related papers  (2021-12-10T16:19:28Z)
• FocusFace: Multi-task Contrastive Learning for Masked Face Recognition [4.420321822469077]
  SARS-CoV-2 has presented direct and indirect challenges to the scientific community. Face recognition methods struggle to perform identity verification with similar accuracy on masked and unmasked individuals. We propose FocusFace, a multi-task architecture that uses contrastive learning to be able to accurately perform masked face recognition.
  arXiv  Detail & Related papers  (2021-10-28T08:17:12Z)
• End2End Occluded Face Recognition by Masking Corrupted Features [82.27588990277192]
  State-of-the-art general face recognition models do not generalize well to occluded face images. This paper presents a novel face recognition method that is robust to occlusions based on a single end-to-end deep neural network. Our approach, named FROM (Face Recognition with Occlusion Masks), learns to discover the corrupted features from the deep convolutional neural networks, and clean them by the dynamically learned masks.
  arXiv  Detail & Related papers  (2021-08-21T09:08:41Z)
• FT-TDR: Frequency-guided Transformer and Top-Down Refinement Network for Blind Face Inpainting [77.78305705925376]
  Blind face inpainting refers to the task of reconstructing visual contents without explicitly indicating the corrupted regions in a face image. We propose a novel two-stage blind face inpainting method named Frequency-guided Transformer and Top-Down Refinement Network (FT-TDR) to tackle these challenges.
  arXiv  Detail & Related papers  (2021-08-10T03:12:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.